Method for adjusting pressure and flow of water supply network

Abstract

The invention belongs to the technical field of water supply network adjustment, and particularly relates to a water supply network pressure and flow adjusting method. The method comprises the following steps: firstly, collecting pressure, flow and water temperature data of a monitoring node at present and in a preset time period, wherein the preset time period is set according to a water consumption period; preprocessing flow data through a sliding window method and fitting a curve, and marking an instantaneous disturbance time period; the dynamic response coefficient of each disturbance time period is calculated, and water temperature correction is needed; combining the flow standard score, the dynamic response coefficient and the real-time deviation coefficient to obtain a flow dynamic regulation index; a pressure stability index is obtained through pressure and water temperature trend feature vector matching; the two are subjected to weighted fusion to form a pipe network comprehensive regulation factor, and the valve opening and the water pump power are regulated accordingly. The method can accurately identify instantaneous disturbance, improve the adjustment precision and response speed, and guarantee stable water supply.

Description

Technical Field

[0001] This invention belongs to the field of water supply network regulation technology, and particularly relates to a method for regulating the pressure and flow of a water supply network. Background Technology

[0002] Water supply networks are a core component of urban infrastructure, and the stability of their pressure and flow directly affects water supply efficiency, energy consumption control, and user experience. Currently, water supply network regulation largely relies on historical average data to set fixed parameters, making it difficult to adapt to complex and ever-changing water usage scenarios. In actual operation, water demand exhibits significant periodic fluctuations and instantaneous disturbances (such as morning and evening peak water usage, sudden concentrated water usage, etc.). Traditional regulation methods often suffer from dynamic response lag because they fail to effectively identify such instantaneous changes. Simultaneously, water temperature changes affect the hydraulic characteristics of the network, a factor that existing technologies often overlook, leading to insufficient precision in pressure and flow regulation. When faced with sudden increases or decreases in flow, it can easily cause drastic fluctuations in network pressure, not only increasing pump energy consumption but also potentially exacerbating the risk of pipeline leaks. Furthermore, untimely flow supply can affect water supply stability, failing to meet the demand for real-time and precise network regulation. Summary of the Invention

[0003] In view of the technical problems existing in the background art, the present invention proposes a method for regulating the pressure and flow of water supply network.

[0004] To achieve the above objectives, the technical solution adopted by the present invention includes the following steps:

[0005] Collect pressure data, flow data, and water temperature data of all monitoring nodes in the water supply network at the current collection time and within a preset time period, where the preset time period is set according to the water usage cycle;

[0006] Based on the characteristics of traffic data changes at all collection times, the traffic data is preprocessed using the sliding window method and fitted to obtain a traffic trend curve. All traffic surge points and adjacent drop points are extracted from the curve, and the time period from the time corresponding to each surge point to the time corresponding to the adjacent drop point is marked as the instantaneous disturbance period.

[0007] For each instantaneous disturbance period, the ratio of the slope of the pressure data fitting curve to the slope of the flow trend curve within that period is calculated. Combined with the baseline value of the slope ratio of the disturbance periods within the preset period, the dynamic response coefficient of each instantaneous disturbance period is determined. The baseline value of the slope ratio needs to be corrected according to the average water temperature within the period.

[0008] Calculate the actual slope of change of pressure and flow data at all current acquisition times, and calculate the deviation from the slope of change at the same time within a preset time period to obtain the real-time deviation coefficient; based on the standard score, dynamic response coefficient and real-time deviation coefficient of the flow data at the current time after standardization, determine the dynamic adjustment index of the water supply network flow at the current time through weighted product operation.

[0009] Calculate the trend characteristics of all pressure and water temperature data at the current acquisition time, and calculate the real-time trend feature vector; perform cosine similarity matching between the real-time trend feature vector and the stable state feature vector at the same moment within the preset time period to obtain the trend matching degree; perform nonlinear mapping on the obtained trend matching degree to obtain the pressure stability index at the current moment.

[0010] The flow dynamic adjustment index and the pressure stability index are weighted and fused to obtain the comprehensive pipeline network adjustment factor at the current moment; based on this comprehensive pipeline network adjustment factor, the valve opening and pump power are adjusted and corrected.

[0011] Preferably, the preset time period is set according to the water usage cycle, and this is achieved by:

[0012] First, collect three days of flow data from the water supply network. Then, fit the three days of flow data into a flow trend curve using the least squares method, which will be used as the flow data for the preset time period.

[0013] By using a queue approach, the traffic data is updated every time a new day's traffic data is collected, and the traffic curve is refitted using the least squares method to obtain a new traffic trend curve for the preset time period.

[0014] Preferably, the implementation of fitting the flow trend curve after preprocessing the flow data using the sliding window method specifically includes:

[0015] Sort the traffic data by time series and set the time span of the sliding window;

[0016] The window is slid sequentially with the collection time as the step size; outliers are removed from the traffic data in each window.

[0017] For the removed areas, replace the value in that area with the average of the two consecutive valid values ​​within the window;

[0018] The preprocessed window data is fitted with a weighted least squares method to form a continuous flow trend curve by splicing the fitted curve segments of all windows in chronological order.

[0019] Preferably, the method for determining the flow surge point and the adjacent flow drop point is as follows:

[0020] The first derivative of the fitted flow trend curve is used to obtain the flow rate change curve; a threshold for the flow rate change is then set. ;

[0021] When the first derivative value at a certain point in the flow rate change curve changes from negative to positive and exceeds... When this occurs, mark the point as a point of sudden increase in flow.

[0022] When the first derivative of the flow rate change curve at a certain point changes from positive to negative and its absolute value exceeds... At that time, mark the point as the point of sudden drop in flow;

[0023] For multiple consecutive increase points, the point with the largest first derivative value is taken as the effective increase point; for multiple consecutive decrease points, the point with the largest absolute value of the first derivative value is taken as the effective decrease point.

[0024] Pair up and down points that are adjacent in time to form the start and end boundaries of the instantaneous disturbance period.

[0025] Preferably, the determination of the dynamic response coefficient for each instantaneous disturbance period specifically includes:

[0026] Pressure data for each instantaneous disturbance period are preprocessed and fitted using the same sliding window method as the flow trend curve to generate a pressure fitting curve; the average slope of the pressure fitting curve for that instantaneous disturbance period is then calculated. and the average slope of the flow trend curve To obtain the actual slope ratio ;

[0027] Extract the pressure-flow rate slope ratios for all disturbance periods within a preset time period, and calculate their arithmetic mean as the initial baseline value. ;

[0028] Based on the average water temperature during the instantaneous disturbance period Calculate the water temperature correction factor The correction coefficient is calculated as follows: ,in As the reference water temperature, This refers to the temperature sensitivity coefficient.

[0029] The correction coefficients obtained from the root cause are relative to the initial reference value. Make corrections to obtain the corrected baseline value. ;

[0030] Finally, the dynamic response coefficient is calculated. ,in To adjust the sensitivity coefficient and dynamic response coefficient The value ranges from 0 to 1.

[0031] Preferably, the method for calculating the deviation between the actual change slope of pressure and flow data at all current acquisition times and the change slope at the same time within a preset time period to obtain the real-time deviation coefficient is as follows:

[0032] Take the pressure and flow data sequences collected at the current acquisition time and the previous four acquisition times, and use linear regression to fit the actual pressure change slope. and the slope of actual flow rate change Calculate the actual slope ratio ;

[0033] Obtain the slope ratio of changes within the same period in the preset time period Calculate the deviation coefficient .

[0034] As a preferred method, the dynamic regulation index of the water supply network at the current moment is determined by weighted product calculation based on the standardized score, dynamic response coefficient, and real-time deviation coefficient of the flow data at the current moment.

[0035] First, the current traffic data is standardized to obtain a standardized score. ;

[0036] If the current moment belongs to the instantaneous disturbance period, select the dynamic response coefficient corresponding to the instantaneous disturbance period to which the current moment belongs. If the current moment is not within the instantaneous disturbance period, then the arithmetic mean of all dynamic response coefficients within the preset period is taken. ;

[0037] The dynamic flow regulation index is obtained through weighted product calculation. Where i = 1, 2, and when i is 1, it is... When taking 2, it is , These are weighting coefficients, and .

[0038] Preferably, the implementation of the pressure stability coefficient at the current moment specifically includes:

[0039] First, pressure and water temperature data sequences were collected at the previous acquisition time and the four acquisition times prior to this time, and fitted into curves. The consistency of change direction and the consistency of fluctuation amplitude were calculated. The consistency of change direction was calculated by using the Pearson correlation coefficient to determine the degree of fit between the change direction of pressure and water temperature, and the consistency of fluctuation amplitude was calculated by using the normalized ratio of the fluctuation amplitude of pressure and water temperature. The two types of features were then concatenated to obtain a real-time trend feature vector.

[0040] If the current time is determined to be within a transient disturbance period, the trend feature vectors of all transient disturbance periods within the preset time period that are concurrent with the current time are extracted, and their mean is calculated as the disturbance baseline feature vector; if the current time is not within a transient disturbance period, the trend feature vectors of all non-disturbance periods within the preset time period that are concurrent with the current time are extracted, and their mean is calculated as the stable baseline feature vector.

[0041] Real-time trend feature vectors are calculated using cosine similarity. Its corresponding reference vector The matching degree is used to obtain the trend matching degree Sim, where j=1, 2; when j=1, it is the perturbation baseline feature vector, and when j=2, it is the stable baseline feature vector.

[0042] By performing a nonlinear mapping on the trend matching degree, the pressure stability coefficient at the current moment is obtained. The calculation method is as follows: ,in When j is 1, the trend matching degree is obtained. The trend matching degree is obtained when j is 2.

[0043] As a preferred approach, the dynamic flow regulation index and the pressure stability index are weighted and fused to obtain the comprehensive pipeline regulation factor at the current moment. Based on this comprehensive pipeline regulation factor, the adjustment and correction of valve opening and pump power are implemented as follows:

[0044] First, the flow dynamic adjustment index and the pressure stability index are weighted and fused to obtain the comprehensive pipeline network adjustment factor at the current moment. ,in These are the weighting coefficients;

[0045] Classification is performed based on preset comprehensive pipeline regulation factor thresholds. If the value is less than or equal to the threshold, only the valve opening is adjusted. The calculation formula is as follows: ,in This is the initial valve opening value. This represents the corrected valve opening value;

[0046] like If the value exceeds the threshold, both the threshold opening and the pump power will be adjusted. The valve opening adjustment correction method is as follows: The water pump power adjustment correction method is as follows: ,in This is the initial pump power value. This is the corrected pump power value.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are:

[0048] 1. By preprocessing flow data using the sliding window method and combining it with first-order derivative analysis to extract flow surge and drop points, instantaneous disturbance periods are accurately marked. Dynamic response coefficients are then calculated separately for these periods, enabling rapid capture of instantaneous changes in the pipeline network and making regulation strategies more targeted.

[0049] 2. By correcting the slope ratio benchmark value with a water temperature correction coefficient, the influence of water temperature changes on the relationship between pressure and flow is fully considered, making the adjustment of pressure and flow more in line with the actual hydraulic characteristics and significantly improving the control accuracy.

[0050] 3. Based on threshold classification of comprehensive adjustment factors, a tiered adjustment method is adopted: when the factor is small, only the valve opening is adjusted to achieve slight correction; when the factor is large, both the valve opening and the pump power are adjusted simultaneously for deep regulation. This strategy ensures water supply stability while reducing unnecessary energy consumption and lowering the risk of pipeline leakage, thus balancing economy and safety. Attached Figure Description

[0051] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a structural flowchart of a method for regulating the pressure and flow of a water supply network. Detailed Implementation

[0053] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described below in conjunction with the accompanying drawings and embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways than those described herein. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] In this embodiment, current water supply network regulation largely relies on historical average data to set fixed parameters, which is difficult to adapt to complex and ever-changing water usage scenarios. In actual operation, water demand exhibits significant periodic fluctuations and instantaneous disturbances (such as morning and evening peak water usage, sudden concentrated water usage, etc.). Traditional regulation methods often suffer from dynamic response lag because they fail to effectively identify such instantaneous changes. Therefore, this invention proposes a method for regulating the pressure and flow of a water supply network. Specific implementation steps are as follows: Figure 1 As shown.

[0056] First, pressure, flow, and water temperature data of all monitoring nodes in the water supply network are collected at the current acquisition time and within a preset time period, where the preset time period is set according to the water usage cycle. The implementation of setting the preset time period according to the water usage cycle includes: first, collecting three days of flow data from the water supply network, fitting the three days of flow data into a flow trend curve using the least squares method, and using this curve as the flow data within the preset time period; then, using a queue method, updating the data each time a new day's flow data is collected, and re-fitting the flow curve using the least squares method to obtain a new flow trend curve for the preset time period.

[0057] Based on the characteristics of traffic flow data changes at all acquisition times, a traffic flow trend curve is obtained by preprocessing the traffic flow data using the sliding window method. All traffic flow spikes and adjacent drops are extracted from the curve, and the time interval between each spike and the adjacent drop is marked as the instantaneous disturbance period. Specifically, the process of preprocessing the traffic flow data using the sliding window method to obtain the traffic flow trend curve includes: sorting the traffic flow data by time series and setting the time span of the sliding window; sliding the window sequentially with the acquisition time as the step size; removing outliers from the traffic flow data within each window; replacing the value of the removed area with the average of the two adjacent valid values ​​within the window; and using weighted least squares to fit the preprocessed window data to the curve, then stitching the fitted curve segments of all windows together in chronological order to form a continuous traffic flow trend curve. Specifically, after sorting the original traffic flow data chronologically, a sliding window with a fixed time span is first set, and then shifted sequentially along the sequence with the data acquisition time as the step size. Whenever the window moves, outlier removal is performed on the flow sequence within the window: for peaks and troughs exceeding the statistical threshold, the average of the peak and trough is taken and replaced with the average of the two nearest valid data sets to eliminate interference from sudden noise on trend fitting. After outlier handling, weighted least squares is applied to the purified data within the window for curve fitting, with data near the window center given higher weights based on chronological order to ensure the accuracy of the fitted curve at critical moments. The local fitting results of all windows are seamlessly stitched together in chronological order to obtain a smooth and continuous flow trend curve, which preserves the overall trend while smoothing out short-term fluctuations, facilitating the accurate extraction of subsequent disturbance points and the real-time calculation of pipeline regulation parameters.

[0058] The method for determining the flow surge point and adjacent drop point is as follows: Calculate the first derivative of the fitted flow trend curve to obtain the flow change rate curve; set a flow change rate threshold. When the first derivative value at a certain point in the flow rate change curve changes from negative to positive and exceeds... When the first derivative of a point on the flow rate change curve changes from positive to negative and its absolute value exceeds a certain threshold, the point is marked as the point of sudden flow increase. When the flow rate drops, mark the point as the point of sudden decrease; for multiple consecutive surge points, take the point with the largest first derivative value as the effective surge point; for multiple consecutive decrease points, take the point with the largest absolute value of the first derivative value as the effective decrease point; pair up the effective surge points and effective decrease points that are adjacent in time to form the start and end boundaries of the instantaneous disturbance period.

[0059] For each instantaneous disturbance period, the ratio of the slope of the pressure data fitting curve to the slope of the flow trend curve within that period is calculated. Combined with a preset baseline value for the slope ratio of disturbance periods within a given time period, the dynamic response coefficient for each instantaneous disturbance period is determined. The baseline value for the slope ratio needs to be corrected based on the average water temperature within that time period. Specifically, determining the dynamic response coefficient for each instantaneous disturbance period includes: applying the same sliding window preprocessing and fitting method as the flow trend curve to the pressure data within each instantaneous disturbance period to generate a pressure fitting curve; and calculating the average slope of the pressure fitting curve within that instantaneous disturbance period. and the average slope of the flow trend curve To obtain the actual slope ratio Extract the pressure-flow rate slope ratios for all disturbance periods within the preset time period, and calculate their arithmetic mean as the initial baseline value. Based on the average water temperature during the instantaneous disturbance period Calculate the water temperature correction factor The correction coefficient is calculated as follows: ,in As the reference water temperature, The temperature sensitivity coefficient; the correction coefficient obtained from the root cause relative to the initial reference value. Make corrections to obtain the corrected baseline value. Finally, calculate the dynamic response coefficient. ,in To adjust the sensitivity coefficient and dynamic response coefficient The value ranges from 0 to 1.

[0060] The actual slope of pressure and flow data at all current acquisition times is calculated, and the deviation from the slope at the same time within a preset time period is calculated to obtain a real-time deviation coefficient. Based on the standardized score, dynamic response coefficient, and real-time deviation coefficient of the flow data at the current time after standardization, the dynamic adjustment index of the water supply network at the current time is determined by weighted product operation. Specifically, the method for calculating the actual slope of pressure and flow data at all current acquisition times and the deviation from the slope at the same time within a preset time period to obtain the real-time deviation coefficient is as follows: the pressure data sequence and flow data sequence collected at the current acquisition time and the previous four acquisition times are taken, and the actual slope of pressure change is obtained by fitting them with linear regression. and the slope of actual flow rate change Calculate the actual slope ratio ; Obtain the slope ratio of changes within the same period in a preset time period Calculate the deviation coefficient Then, based on the standardized scores, dynamic response coefficients, and real-time deviation coefficients of the current flow data, the dynamic regulation index of the water supply network at the current moment is determined through a weighted product operation. The calculation method is as follows: First, the flow data at the current moment is standardized to obtain the standardized scores. If the current moment belongs to the instantaneous disturbance period, select the dynamic response coefficient corresponding to the instantaneous disturbance period to which the current moment belongs. If the current moment is not within the instantaneous disturbance period, then the arithmetic mean of all dynamic response coefficients within the preset period is taken. The dynamic flow regulation index is obtained through weighted product calculation. Where i = 1, 2, and when i is 1, it is... When taking 2, it is , These are weighting coefficients, and .

[0061] Calculate the trend characteristics of all pressure and water temperature data at the current acquisition time, and calculate the real-time trend feature vector; perform cosine similarity matching between the real-time trend feature vector and the stable state feature vector at the same moment within the preset time period to obtain the trend matching degree; perform nonlinear mapping on the obtained trend matching degree to obtain the pressure stability index at the current moment. Specifically, the realization of the pressure stability coefficient at the current moment includes: firstly, collecting pressure data sequences and water temperature data sequences from the previous four collection moments, fitting them into curves, and calculating the consistency of change direction and the consistency of fluctuation amplitude; the consistency of change direction is calculated using the Pearson correlation coefficient to determine the degree of fit between the pressure and water temperature change directions, and the consistency of fluctuation amplitude is calculated using the normalized ratio of pressure and water temperature fluctuation amplitudes; the two types of features are concatenated to obtain a real-time trend feature vector; if the current moment belongs to a transient disturbance period, the trend feature vectors of the same period as the current moment are extracted from all transient disturbance periods within a preset period, and their mean is calculated as the disturbance baseline feature vector; if the current moment is not in a transient disturbance period, the trend feature vectors of the same period as the current moment are extracted from all non-disturbance periods within a preset period, and their mean is calculated as the stability baseline feature vector; the real-time trend feature vector is calculated using cosine similarity. Its corresponding reference vector The matching degree is used to obtain the trend matching degree Sim, where j=1, 2; when j=1, it is the disturbance baseline feature vector, and when j=2, it is the stability baseline feature vector; the trend matching degree is then nonlinearly mapped to obtain the pressure stability coefficient at the current time. The calculation method is as follows: ,in When j is 1, the trend matching degree is obtained. The trend matching degree is obtained when j is 2.

[0062] Finally, the flow dynamic regulation index and the pressure stability index are weighted and fused to obtain the comprehensive pipeline regulation factor at the current moment. Based on this comprehensive pipeline regulation factor, the valve opening and pump power are adjusted and corrected. Specifically, firstly, the flow dynamic regulation index and the pressure stability index are weighted and fused to obtain the comprehensive pipeline regulation factor at the current moment. ,in As the weighting coefficient; classification is performed based on a preset threshold for the comprehensive pipeline network adjustment factor, if If the value is less than or equal to the threshold, only the valve opening is adjusted. The calculation formula is as follows: ,in This is the initial valve opening value. This represents the corrected valve opening value; if If the value exceeds the threshold, both the threshold opening and the pump power will be adjusted. The valve opening adjustment correction method is as follows: The water pump power adjustment correction method is as follows: ,in This is the initial pump power value. This is the corrected pump power value.

[0063] The above description is merely a preferred embodiment of the present invention and does not constitute any other form of limitation to the present invention. Any person skilled in the art may utilize the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes for application in other fields. However, any simple modification, equivalent change, and modification of the above embodiments made in accordance with the technical essence of the present invention without departing from the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A method for regulating the pressure and flow rate of a water supply network, characterized in that, Includes the following steps: Collect pressure data, flow data, and water temperature data of all monitoring nodes in the water supply network at the current collection time and within a preset time period, where the preset time period is set according to the water usage cycle; Based on the characteristics of traffic data changes at all collection times, the traffic data is preprocessed using the sliding window method and fitted to obtain a traffic trend curve. All traffic surge points and adjacent drop points are extracted from the curve, and the time period from the time corresponding to each surge point to the time corresponding to the adjacent drop point is marked as the instantaneous disturbance period. For each instantaneous disturbance period, the ratio of the slope of the pressure data fitting curve to the slope of the flow trend curve within that period is calculated. Combined with the baseline value of the slope ratio of the disturbance periods within the preset period, the dynamic response coefficient of each instantaneous disturbance period is determined. The baseline value of the slope ratio needs to be corrected according to the average water temperature within the period. Calculate the actual slope of change of pressure and flow data at all current acquisition times, and calculate the deviation from the slope of change at the same time within a preset time period to obtain the real-time deviation coefficient; based on the standard score, dynamic response coefficient and real-time deviation coefficient of the flow data at the current time after standardization, determine the dynamic adjustment index of the water supply network flow at the current time through weighted product operation. Calculate the trend characteristics of pressure and water temperature data at all current acquisition times, and calculate the real-time trend feature vector; The trend matching degree is obtained by performing cosine similarity matching between the real-time trend feature vector and the stable state feature vector at the same moment within a preset time period. The obtained trend matching degree is non-linearly mapped to obtain the pressure stability index at the current moment; The flow dynamic adjustment index and the pressure stability index are weighted and fused to obtain the comprehensive pipeline network adjustment factor at the current moment; Based on the comprehensive adjustment factor of the pipeline network, the valve opening and pump power are adjusted and corrected.

2. The method for regulating pressure and flow in a water supply network according to claim 1, characterized in that, The implementation of the preset time period based on the water usage cycle includes: First, collect three days of flow data from the water supply network. Then, fit the three days of flow data into a flow trend curve using the least squares method, which will be used as the flow data for the preset time period. By using a queue approach, the traffic data is updated every time a new day's traffic data is collected, and the traffic curve is refitted using the least squares method to obtain a new traffic trend curve for the preset time period.

3. The method for regulating the pressure and flow rate of a water supply network according to claim 1, characterized in that, The specific implementation of fitting the flow trend curve after preprocessing the flow data using the sliding window method includes: Sort the traffic data by time series and set the time span of the sliding window; The window is slid sequentially with the collection time as the step size; outliers are removed from the traffic data in each window. For the removed areas, replace the value in that area with the average of the two consecutive valid values ​​within the window; The preprocessed window data is fitted with a weighted least squares method to form a continuous flow trend curve by splicing the fitted curve segments of all windows in chronological order.

4. The method for regulating the pressure and flow rate of a water supply network according to claim 1, characterized in that, The method for determining the flow surge point and the adjacent drop point is as follows: The first derivative of the fitted flow trend curve is used to obtain the flow rate change curve; a threshold for the flow rate change is then set. ; When the first derivative value at a certain point in the flow rate change curve changes from negative to positive and exceeds... When this occurs, mark the point as a point of sudden increase in flow. When the first derivative of the flow rate change curve at a certain point changes from positive to negative and its absolute value exceeds... At that time, mark the point as the point of sudden drop in flow; For multiple consecutive increase points, the point with the largest first derivative value is taken as the effective increase point; for multiple consecutive decrease points, the point with the largest absolute value of the first derivative value is taken as the effective decrease point. Pair up and down points that are adjacent in time to form the start and end boundaries of the instantaneous disturbance period.

5. The method for regulating the pressure and flow rate of a water supply network according to claim 1, characterized in that, The specific implementation of determining the dynamic response coefficients for each instantaneous disturbance period includes: Pressure data for each instantaneous disturbance period are preprocessed and fitted using the same sliding window method as the flow trend curve to generate a pressure fitting curve; the average slope of the pressure fitting curve for that instantaneous disturbance period is then calculated. and the average slope of the flow trend curve To obtain the actual slope ratio ; Extract the pressure-flow rate slope ratios for all disturbance periods within a preset time period, and calculate their arithmetic mean as the initial baseline value. ; Based on the average water temperature during the instantaneous disturbance period Calculate the water temperature correction factor The correction coefficient is calculated as follows: ,in As the reference water temperature, This refers to the temperature sensitivity coefficient. The correction coefficients obtained from the root cause are relative to the initial reference value. Make corrections to obtain the corrected baseline value. ; Finally, the dynamic response coefficient is calculated. ,in To adjust the sensitivity coefficient and dynamic response coefficient The value ranges from 0 to 1.

6. The method for regulating pressure and flow in a water supply network according to claim 1, characterized in that, The method for calculating the actual slope of pressure and flow data at all current acquisition times and the deviation between this slope and the slope at the same time within a preset time period to obtain the real-time deviation coefficient is as follows: Take the pressure and flow data sequences collected at the current acquisition time and the previous four acquisition times, and use linear regression to fit the actual pressure change slope. and the slope of actual flow rate change Calculate the actual slope ratio ; Obtain the slope ratio of changes within the same period in the preset time period Calculate the deviation coefficient .

7. The method for regulating the pressure and flow rate of a water supply network according to claim 6, characterized in that, Based on the standardized scores, dynamic response coefficients, and real-time deviation coefficients of the current flow data, the dynamic regulation index of the water supply network at the current moment is determined by weighted product calculation as follows: First, the current traffic data is standardized to obtain a standardized score. ; If the current moment belongs to the instantaneous disturbance period, select the dynamic response coefficient corresponding to the instantaneous disturbance period to which the current moment belongs. If the current moment is not within the instantaneous disturbance period, then the arithmetic mean of all dynamic response coefficients within the preset period is taken. ; The dynamic flow regulation index is obtained through weighted product calculation. Where i = 1, 2, and when i is 1, it is... When taking 2, it is , These are weighting coefficients, and .

8. The method for regulating the pressure and flow rate of a water supply network according to claim 1, characterized in that, The implementation of the pressure stability coefficient at the current moment specifically includes: First, pressure and water temperature data sequences were collected at the previous acquisition time and the four acquisition times prior to this time, and fitted into curves. The consistency of change direction and the consistency of fluctuation amplitude were calculated. The consistency of change direction was calculated by using the Pearson correlation coefficient to determine the degree of fit between the change direction of pressure and water temperature, and the consistency of fluctuation amplitude was calculated by using the normalized ratio of the fluctuation amplitude of pressure and water temperature. The two types of features were then concatenated to obtain a real-time trend feature vector. If the current time is determined to be within a transient disturbance period, the trend feature vectors of all transient disturbance periods within the preset time period that are concurrent with the current time are extracted, and their mean is calculated as the disturbance baseline feature vector; if the current time is not within a transient disturbance period, the trend feature vectors of all non-disturbance periods within the preset time period that are concurrent with the current time are extracted, and their mean is calculated as the stable baseline feature vector. Real-time trend feature vectors are calculated using cosine similarity. Its corresponding reference vector The matching degree is used to obtain the trend matching degree Sim, where j=1, 2; when j=1, it is the perturbation baseline feature vector, and when j=2, it is the stable baseline feature vector. By performing a nonlinear mapping on the trend matching degree, the pressure stability coefficient at the current moment is obtained. The calculation method is as follows: ,in When j is 1, the trend matching degree is obtained. The trend matching degree is obtained when j is 2.

9. A method for regulating the pressure and flow rate of a water supply network according to claim 1, characterized in that, The flow dynamic adjustment index and the pressure stability index are weighted and fused to obtain the comprehensive pipeline network adjustment factor at the current moment; Based on the comprehensive regulation factor of this pipeline network, the adjustment and correction of valve opening and pump power are achieved as follows: First, the flow dynamic adjustment index and the pressure stability index are weighted and fused to obtain the comprehensive pipeline network adjustment factor at the current moment. ,in These are the weighting coefficients; Classification is performed based on preset comprehensive pipeline regulation factor thresholds. If the value is less than or equal to the threshold, only the valve opening is adjusted. The calculation formula is as follows: ,in This is the initial valve opening value. This represents the corrected valve opening value; like If the value exceeds the threshold, both the threshold opening and the pump power will be adjusted. The valve opening adjustment correction method is as follows: The water pump power adjustment correction method is as follows: ,in This is the initial pump power value. This is the corrected pump power value.

Images